OpenAI
GPT-4 Turbo
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.
At a glance
- Input / 1M
- $10
- Output / 1M
- $30
- Context
- 128K
- Max output
- 4K
- Intelligence
- 7
- Released
- Apr 2024
Pricing
GPT-4 Turbo API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $10 |
|---|---|
| Output tokensPer 1M tokens | $30 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$35
per 1,000 requests
Coding task
30K in, 4K out
$420
per 1,000 requests
Long document summary
150K in, 2K out
$1560
per 1,000 requests
Benchmarks
GPT-4 Turbo benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
7
Coding index
21.5
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 128K tokens
- Max output
- 4K tokens
- Input types
- Image, Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- April 9, 2024
- Knowledge cutoff
- December 31, 2023
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
GPT-4 Turbo vs other models
See how GPT-4 Turbo stacks up head to head on price, benchmarks, and features.
VSGPT-4 Turbo vs o1
OpenAI vs OpenAI
See comparisonVSGPT-4 Turbo vs GPT-4.1
OpenAI vs OpenAI
See comparisonVSGPT-4 Turbo vs o1-pro
OpenAI vs OpenAI
See comparisonVS
GPT-4 Turbo vs Nova Premier 1.0
OpenAI vs Amazon
See comparisonVSGPT-4 Turbo vs GPT-4o (2024-11-20)
OpenAI vs OpenAI
See comparisonVSGPT-4 Turbo vs GPT-4o (2024-08-06)
OpenAI vs OpenAI
See comparisonAlternatives
GPT-4 Turbo alternatives
Similar models worth considering, and where each one has the edge.
OpenAI
GPT-4.1
Amazon
Nova Premier 1.0
OpenAI
GPT-4o (2024-11-20)
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does GPT-4 Turbo cost?
GPT-4 Turbo costs $10 per 1M input tokens and $30 per 1M output tokens through the API. A typical chat message costs about $35 per 1,000 messages.
What is the context window of GPT-4 Turbo?
GPT-4 Turbo accepts up to 128K tokens of input and can write up to 4K tokens in a single response.
What is the best alternative to GPT-4 Turbo?
GPT-4.1 from OpenAI is a strong alternative. It offers: 3.8x cheaper output, higher intelligence score, larger 1.05m context.
Can I use GPT-4 Turbo alongside other models?
Yes. Shortcut Chat sends one prompt to GPT-4 Turbo and any other models you pick at the same time, so you can compare answers side by side.
Try GPT-4 Turbo next to every other model.
Use GPT-4 Turbo alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.